det["image_id"], det["bbox"][0], det["bbox"][1],
det["bbox"][2], det["bbox"][3], det["score"]
]).unsqueeze(dim=0)
if video_dets.shape[0] == 0:
video_dets = det_t
else:
video_dets = torch.cat([video_dets, det_t])
# 选取这段视频中的score最大的框
used_mask = torch.zeros(video_dets.shape[0])
max_score, max_score_index = select_max_det(video_dets, used_mask)
used_mask[
max_score_index] = True # 标记已经被选择的框，排除后迭代，直到max score小于阈值0.2
gallery_imgs = []
for image_id in ids:
crop_imgs = bridge.crop_img(image_id)
if len(crop_imgs) > 0:
gallery_imgs.extend(crop_imgs)
while (max_score > 0.5):
query_img = bridge.crop_bbox(
int(video_dets[max_score_index][0]),
video_dets[max_score_index][1:5])
# gallery_imgs = []
query_feat = reid.extract_feats([query_img])
gallery_feats = reid.extract_feats(gallery_imgs)
min_dist, min_dist_index = get_similar_box(
query_feat, gallery_feats, used_mask)
position = [
int(video_dets[min_dist_index][1]),
int(video_dets[min_dist_index][2])
